Convolutional Neural Network-based place recognition

Recently Convolutional Neural Networks (CNNs) have been shown to achieve state-of-the-art performance on various classification tasks. In this paper, we present for the first time a place recognition technique based on CNN models, by combining the powerful features learnt by CNNs with a spatial and sequential filter. Applying the system to a 70 km benchmark place recognition dataset we achieve a 75% increase in recall at 100% precision, significantly outperforming all previous state of the art techniques. We also conduct a comprehensive performance comparison of the utility of features from all 21 layers for place recognition, both for the benchmark dataset and for a second dataset with more significant viewpoint changes.

Tools, building blocks, and rewards : traditional media organizations learn to engage with productive audiences

This paper explores how traditional media organizations (such as magazines, music, film, books, and newspapers) develop routines for coping with an increasingly productive audience. While previous studies have reported on how such organizations have been affected by digital technologies, this study makes a contribution to this literature by being one of the first to show how organizational routines for engaging with an increasingly productive audience actually emerge and diffuse between industries. The paper explores to what extent routines employed by two traditional media organizations have been brought in from other organizational settings, specifically from so-called ‘software platform operators’. Data on routines for engaging with productive audiences have been collected from two information-rich cases in the music and the magazine industries, and from eight high-profile software platform operators. The paper concludes that the routines employed by the two traditional media organizations and by the software platform operators are based on the same set of principles: Provide the audience with (a) tools that allow them to easily generate cultural content; (b) building blocks which facilitate their creative activities; and (c) recognition and rewards based on both rationality and emotion.

Shaping safe drinking cultures : evoking positive emotion to promote moderate-drinking behaviour

Social marketing by Western governments that use fear tactics and threatening information to promote anti-drinking messages has polarized ‘binge drinking’ and ‘moderate drinking’ through a continuum that implies benefits and harms for both individuals and society. With the goal of extending insights into social marketing approaches that promote safer drinking cultures in Australia, we discuss findings from a study that examines alcohol consumers' moderate-drinking intentions. By applying the theory of planned behaviour and emotions theory, we discuss survey results from a sample of alcohol consumers, which demonstrate that positively framed value propositions that evoke happiness and love are more influential in the processing of an alcohol moderation message for alcohol consumers. The key limitations of this study are the cross-sectional nature of the data and the focal-dependent variable being behavioural intentions rather than behaviours. Research insight into the stronger influence of positive emotions on processing an alcohol moderation message establishes an important avenue for future social marketing communications that moves beyond negative, avoidance appeals to promote behaviour change in drinkers. These research findings will benefit professionals involved in developing social change campaigns that promote and reinforce consumers' positive intentions, with messages about the benefits of controlled, moderate drinking.

FaceXpress : an integrated software suite for facial emotion stimulus manipulation and facial measurement

The characterisation of facial expression through landmark-based analysis methods such as FACEM (Pilowsky & Katsikitis, 1994) has a variety of uses in psychiatric and psychological research. In these systems, important structural relationships are extracted from images of facial expressions by the analysis of a pre-defined set of feature points. These relationship measures may then be used, for instance, to assess the degree of variability and similarity between different facial expressions of emotion. FaceXpress is a multimedia software suite that provides a generalised workbench for landmark-based facial emotion analysis and stimulus manipulation. It is a flexible tool that is designed to be specialised at runtime by the user. While FaceXpress has been used to implement the FACEM process, it can also be configured to support any other similar, arbitrary system for quantifying human facial emotion. FaceXpress also implements an integrated set of image processing tools and specialised tools for facial expression stimulus production including facial morphing routines and the generation of expression-representative line drawings from photographs.

Navigating emotion research during a paradigm shift in psychology

Human emotional responses are highly individual. A comprehensive analysis of emotion research in cognitive psychology and physiology, including laboratory-based experiments, showed that understanding human emotions requires a dynamic systems approach incorporating insights from scientific disciplines beyond psychology. Importantly, subjective and automatic evaluations of emotive information are context-sensitive and changeable, confirming the dynamic nature of emotion and role of individual differences. Furthermore, a comparison of different statistical approaches established that statistical estimation, rather than averages, best captures our highly individual emotional responses. Emotion research needs a cross-disciplinary approach.

Automated counting of the Northern Pacific Sea Star in the Derwent using shape recognition

A novel shape recognition algorithm was developed to autonomously classify the Northern Pacific Sea Star (Asterias amurenis) from benthic images that were collected by the Starbug AUV during 6km of transects in the Derwent estuary. Despite the effects of scattering, attenuation, soft focus and motion blur within the underwater images, an optimal joint classification rate of 77.5% and misclassification rate of 13.5% was achieved. The performance of algorithm was largely attributed to its ability to recognise locally deformed sea star shapes that were created during the segmentation of the distorted images.

Emotion and its regulation predicts gluten-free diet adherence in adults with coeliac disease

Objective The aim of this study was to explore the mediating and moderating relationships between emotional perceptions of coeliac disease, negative emotional states, emotion regulation, emotional eating and gluten-free diet adherence. Method Adults with coeliac disease (N = 253) were recruited from state organisations of Coeliac Australia and completed an online questionnaire measuring illness perceptions, emotion regulation strategies, negative emotional states, emotional eating and gluten-free diet adherence. Results Participants' levels of depression and anxiety, but not stress or emotional eating, were associated with gluten-free diet adherence. Emotional perception of coeliac disease was also associated with gluten-free diet adherence, and this relationship was partially mediated by depression and anxiety. Furthermore, the emotion regulation strategies of cognitive reappraisal and expressive suppression moderated the relationship between emotional perceptions and depression, but not emotional perceptions and anxiety. Conclusions Interventions to improve dietary adherence for adults with coeliac disease displaying depressive symptoms should aim to increase the use of cognitive reappraisal and reduce the use of expressive suppression. Future studies should also explore mechanisms that may moderate the relationship between emotional perceptions and anxiety.

Localization and place recognition using an ultra-wide band (UWB) radar

This paper presents an approach to mobile robot localization, place recognition and loop closure using a monostatic ultra-wide band (UWB) radar system. The UWB radar is a time-of-flight based range measurement sensor that transmits short pulses and receives reflected waves from objects in the environment. The main idea of the poposed localization method is to treat the received waveform as a signature of place. The resulting echo waveform is very complex and highly depends on the position of the sensor with respect to surrounding objects. On the other hand, the sensor receives similar waveforms from the same positions.Moreover, the directional characteristics of dipole antenna is almost omnidirectional. Therefore, we can localize the sensor position to find similar waveform from waveform database. This paper proposes a place recognitionmethod based on waveform matching, presents a number of experiments that illustrate the high positon estimation accuracy of our UWB radar-based localization system, and shows the resulting loop detection performance in a typical indoor office environment and a forest.

Multi-action recognition via stochastic modelling of optical flow and gradients

In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the proposed approach achieves an accuracy of 78.3%, outperforming a recent HMM-based approach which obtained 71.2%.

Improving out-domain PLDA speaker verification using unsupervised inter-dataset variability compensation approach

Experimental studies have found that when the state-of-the-art probabilistic linear discriminant analysis (PLDA) speaker verification systems are trained using out-domain data, it significantly affects speaker verification performance due to the mismatch between development data and evaluation data. To overcome this problem we propose a novel unsupervised inter dataset variability (IDV) compensation approach to compensate the dataset mismatch. IDV-compensated PLDA system achieves over 10% relative improvement in EER values over out-domain PLDA system by effectively compensating the mismatch between in-domain and out-domain data.

Towards robust automatic affective classification of images using facial expressions for practical applications

Affect is an important feature of multimedia content and conveys valuable information for multimedia indexing and retrieval. Most existing studies for affective content analysis are limited to low-level features or mid-level representations, and are generally criticized for their incapacity to address the gap between low-level features and high-level human affective perception. The facial expressions of subjects in images carry important semantic information that can substantially influence human affective perception, but have been seldom investigated for affective classification of facial images towards practical applications. This paper presents an automatic image emotion detector (IED) for affective classification of practical (or non-laboratory) data using facial expressions, where a lot of “real-world” challenges are present, including pose, illumination, and size variations etc. The proposed method is novel, with its framework designed specifically to overcome these challenges using multi-view versions of face and fiducial point detectors, and a combination of point-based texture and geometry. Performance comparisons of several key parameters of relevant algorithms are conducted to explore the optimum parameters for high accuracy and fast computation speed. A comprehensive set of experiments with existing and new datasets, shows that the method is effective despite pose variations, fast, and appropriate for large-scale data, and as accurate as the method with state-of-the-art performance on laboratory-based data. The proposed method was also applied to affective classification of images from the British Broadcast Corporation (BBC) in a task typical for a practical application providing some valuable insights.